Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2453 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.8055. Min Act: -0.1700

Data Index: 6681428 (Open Web Text)

Max Activating Token Index: 167

Text #1

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.7490. Min Act: -0.1700

Data Index: 1747350 (Open Web Text)

Max Activating Token Index: 531

Text #2

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.7304. Min Act: -0.1700

Data Index: 5219337 (Open Web Text)

Max Activating Token Index: 397

Text #3

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.7379. Min Act: -0.1700

Data Index: 5234589 (Open Web Text)

Max Activating Token Index: 63

Text #4

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.7395. Min Act: -0.1700

Data Index: 497675 (Open Web Text)

Max Activating Token Index: 416

Text #5

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.7344. Min Act: -0.1700

Data Index: 65209 (Open Web Text)

Max Activating Token Index: 344

Text #6

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.7363. Min Act: -0.1700

Data Index: 7709654 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.7454. Min Act: -0.1700

Data Index: 8753873 (Open Web Text)

Max Activating Token Index: 333

Text #8

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.7261. Min Act: -0.1700

Data Index: 5219350 (Open Web Text)

Max Activating Token Index: 487

Text #9

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.7167. Min Act: -0.1700

Data Index: 2934060 (Open Web Text)

Max Activating Token Index: 638

Text #10

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.7148. Min Act: -0.1700

Data Index: 6607383 (Open Web Text)

Max Activating Token Index: 197

Text #11

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.7080. Min Act: -0.1700

Data Index: 1069751 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.7171. Min Act: -0.1700

Data Index: 308567 (Open Web Text)

Max Activating Token Index: 419

Text #13

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.7206. Min Act: -0.1700

Data Index: 7122764 (Open Web Text)

Max Activating Token Index: 640

Text #14

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.7091. Min Act: -0.1700

Data Index: 384262 (Open Web Text)

Max Activating Token Index: 464

Text #15

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.7117. Min Act: -0.1700

Data Index: 4211338 (Open Web Text)

Max Activating Token Index: 621

Text #16

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.7106. Min Act: -0.1700

Data Index: 7434256 (Open Web Text)

Max Activating Token Index: 645

Text #17

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.7160. Min Act: -0.1700

Data Index: 7369319 (Open Web Text)

Max Activating Token Index: 523

Text #18

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.6774. Min Act: -0.1700

Data Index: 2360286 (Open Web Text)

Max Activating Token Index: 578

Text #19

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.6907. Min Act: -0.1700

Data Index: 7122749 (Open Web Text)

Max Activating Token Index: 704